Update README.md

README.md

@@ -17,11 +17,33 @@ language:
 
 Bimba is *almost* linear SimulMT model trained with wait-k policy (k = 3, 5, 7, 9, 11) on en-ru translation dataset. 
 
+## Architecture
+
 The model has encoder-decoder architecture, where self-attention blocks are Mamba-2 blocks instead. It means that encoder is linear, but cross-attention's input is all outputs of encoder, and this means that complexity of Bimba is O(S * T), which is not *exactly* linear
 
 ![Bimba inference](https://huggingface.co/OldestSalt/Bimba/resolve/main/hybrid.png)
 
-Bimba was developed as a part of master's thesis, and I hope that I can continue research in Linear SimulMT field.
+Bimba was developed and trained as a part of master's thesis, and I hope that I will continue research in the Linear SimulMT field.
+
+## Using
+
+To download Bimba you can clone GitHub repository and use the HybridMamba2MT class:
+
+```python
+from model_classes import HybridMamba2MT
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("OldestSalt/Bimba")
+model = HybridMamba2MT.from_pretrained("OldestSalt/Bimba")
+```
+
+### Translation
+
+Maybe someday I will write here an example of simultaneous translation
+
+## Tokenizer
+
+This model was distilled from [NLLB-200-1.3B](https://huggingface.co/facebook/nllb-200-1.3B), so Bimba uses its' 
 
 - Code: https://github.com/OldestSalt/LinearSimultMT
-- Paper: Soon
+- Paper: Soon (I hope)